JP6927787B2 - On-board unit and driving support device - Google Patents

Description

The present invention relates to an in-vehicle device and a driving support device having an image processing unit that inputs and processes a video signal output by an in-vehicle camera.

In recent years, vehicles tend to be equipped with an in-vehicle device having an image processing unit that inputs and processes a video signal obtained by shooting with an in-vehicle camera. For example, a general in-vehicle device having a drive recorder function inputs an image signal of an in-vehicle camera, and when an abnormality such as a traffic accident occurs in the own vehicle, the image data within a certain period of time before and after the trigger signal is automatically output. Can be recorded as a vehicle. In addition, some in-vehicle devices having a function of a digital tachograph, which is an operation recorder, input and process the video signal of the in-vehicle camera.

Further, for example, in the navigation device for a vehicle shown in Patent Document 1, when performing image recognition for image information around its own position, the recognition condition of the image recognition process is variably set, so that the arithmetic processing load is increased. It shows a technique for suppressing false recognition and increasing the recognition rate while reducing the problem. Specifically, the range in which the image recognition processing for each target feature with respect to the image information is performed is set according to the degree of self-confidence.

Further, Patent Document 2 shows a vehicle peripheral monitoring device that switches and displays an image of a scene around a vehicle between wide area display and enlarged display. In addition, the captured wide-area shooting data can be converted into wide-area display data for displaying the same field of view on the display device and enlarged display data for displaying a part of the wide-area shooting data in an enlarged manner. It shows that it will be done. Further, it is shown that when the "front" button is operated while the wide area display data is displayed, the area corresponding to the "front" in the wide area shooting data is enlarged and displayed.

Japanese Unexamined Patent Publication No. 2008-298697 Japanese Unexamined Patent Publication No. 2008-301091

By the way, for example, in-vehicle devices such as digital tachographs are desired to be equipped with various driving support functions such as (1) to (3) shown below.
(1) A function that outputs an alarm when the inter-vehicle distance between the own vehicle and the preceding vehicle is too close.
(2) A function that outputs an alarm when the own vehicle deviates from the range of a predetermined traveling lane.
(3) A function that outputs an alarm regarding the overspeed of the own vehicle with respect to the speed limit recognized based on the road surface marking.

When realizing the above functions (1) to (3), for example, it is possible to perform various pattern recognition by processing a video signal representing a scene in front of the own vehicle taken by the in-vehicle camera of the own vehicle. You will need it. That is, based on the image data obtained from the video signal, it is necessary to recognize the pattern of the preceding vehicle, the pattern such as the white line indicating the left-right boundary of the traveling lane, the speed limit marking pattern marked on the road surface, and the like.

In addition, as for the in-vehicle camera mounted on the vehicle, in addition to the in-vehicle camera that captures the front of the own vehicle, the in-vehicle camera that captures the scene behind the own vehicle and the in-vehicle camera that captures the occupants in the vehicle interior are included. There is also. Therefore, in the vehicle-mounted device, it may be necessary to simultaneously process a plurality of video signals output by each of the plurality of vehicle-mounted cameras.

However, in order to simultaneously recognize multiple patterns in real time from images that change sequentially as the vehicle travels, etc., expensive hardware such as a high-performance image processing processor or a high-performance microcomputer The wear must be mounted on the in-vehicle device, and there is a concern that the device cost will increase. However, when trying to realize the above functions with relatively low-cost hardware, it becomes difficult to output various alarms for supporting safe driving in real time because the recognition process of each pattern is delayed.

Therefore, as shown in, for example, Patent Document 1 and Patent Document 2, it is assumed that the range to be subject to image processing in the image is limited in advance. By limiting the range, the load of image processing is reduced, so that the delay in recognition processing can be suppressed to some extent even when relatively low-cost hardware is used.

However, when trying to realize a plurality of functions as described in (1) to (3) at the same time, it is necessary to simultaneously recognize a plurality of recognition targets appearing in different regions in the same video frame, and the recognition target must be recognized. The range cannot be narrowed. As a result, the amount of data in the recognition target range increases, and the delay in the recognition process increases. Further, even when processing the images of a plurality of in-vehicle cameras, it is necessary to expand the range of the objects in consideration of the possibility that the recognition object exists in various places in the image frame.

In addition, since the important areas to be noted in the video frame are different from each other depending on whether the own vehicle is in the forward, stopped, or backward state, in order to make the important area recognizable in any state. , The limitation of the range of recognition must be relaxed. Therefore, the amount of data in the recognition target range increases, and the delay in the recognition process increases.

The present invention has been made in view of the above circumstances, and an object of the present invention is to enable recognition of an important region in any of a plurality of states such as forward movement, stoppage, and backward movement of the own vehicle, and image processing. It is an object of the present invention to provide an in-vehicle device and a driving support device capable of reducing the load of the vehicle.

In order to achieve the above-mentioned object, the on-board unit and the driving support device according to the present invention are characterized by the following (1) to (5).
(1) An image processing unit that inputs and processes video signals output by an in-vehicle camera capable of photographing the rear of the vehicle, and an image processing unit.
A vehicle condition detection unit that detects at least one of the presence / absence of traveling and the traveling direction of the vehicle, and
An image area determination unit that dynamically determines an area in the video signal processed by the image processing unit, and an image area determination unit.
Have,
The image area determination unit, reflecting the detection state of the vehicle state detection unit, automatically changing the area,
The image area determination unit recognizes one of the forward, backward, and stopped states of the vehicle based on the detection state of the vehicle state detection unit.
The image processing unit processes the number or size of the regions processed by the image processing unit when the forward movement of the vehicle is recognized, when the backward movement of the vehicle is recognized and when the stop of the vehicle is recognized. Less than the number or size of the regions,
An in-vehicle device characterized by that.

According to the in-vehicle device having the above (1) and (4) configurations, the region in the video signal processed by the image processing unit can be dynamically determined according to the detection state of the vehicle state detection unit. Therefore, for example, it is possible to recognize an important area in any of a plurality of states such as forward, stop, and reverse of the own vehicle, and the area is optimized so that the amount of data to be processed is reduced. The load can be reduced.
Further, since any one of the forward, backward, and stop states of the vehicle can be recognized, an appropriate area according to the state can be assigned as the processing target of the image processing unit. That is, in any of the forward, backward, and stop states of the vehicle, only the important region of interest in the video frame can be processed, and the region can be optimized so that the amount of data is reduced.

(2) The image area determination unit is
It has a constant holding unit that holds constant data representing the position and size of each of a plurality of two-dimensional regions allocated in advance in the video signal.
One or more two-dimensional regions selected according to the detection state of the vehicle state detection unit from the plurality of two-dimensional regions are allocated as regions in the video signal processed by the image processing unit.
The on-board unit according to (1) above.

According to the in-vehicle device having the configuration of (2) above, the image area determination unit can easily determine an appropriate position and size of the area processed by the image processing unit based on the constant data held by the constant holding unit. Can be decided.

(3) The image area determination unit automatically determines the number of two-dimensional areas to be selected from the plurality of two-dimensional areas and a combination thereof according to the detection state of the vehicle state detection unit.
The on-board unit according to (2) above.

According to the in-vehicle device having the configuration of (3) above, for example, a plurality of two-dimensional regions can be simultaneously assigned to each of a plurality of states such as forward, stop, and reverse of the own vehicle, and the number of two-dimensional regions and The combination can also be optimized. In addition, even when a plurality of important points of interest in a video frame are dispersed at positions separated from each other, the size of each two-dimensional region can be reduced by allocating a plurality of two-dimensional regions at the same time. However, the amount of data processed by the image processing unit can be significantly reduced.

(4) The number or size of the area processed by the image processing unit when the stop of the vehicle is recognized is the number or size of the area processed by the image processing unit when the vehicle is recognized as backward. Smaller than
The on-board unit according to any one of (1) to (3) above.

(5) The on-board unit according to any one of (1) to (4) above, and
An alarm generation unit that generates an alarm that supports safe driving of the vehicle based on the result recognized by the image processing unit from the video signal and a predetermined determination criterion.
A driving support device characterized by being equipped with.

According to the driving support device having the configuration of (5) above, the region in the video signal processed by the image processing unit can be dynamically determined according to the detection state of the vehicle state detection unit. Therefore, even when a function of simultaneously recognizing a plurality of moving objects from an input video frame and outputting a plurality of types of alarms is realized, the amount of data to be processed can be reduced and the delay of the alarms can be suppressed.

According to the on-board unit and the driving support device of the present invention, it is possible to recognize an important area in any of a plurality of states such as forward, stop, and reverse of the own vehicle, and it is possible to reduce the load of image processing. Become.

The present invention has been briefly described above. Further, the details of the present invention will be further clarified by reading through the embodiments described below (hereinafter referred to as "embodiments") with reference to the accompanying drawings. ..

FIG. 1 is a block diagram showing a configuration example of an operation management system according to an embodiment of the present invention. FIG. 2 is a flowchart showing an operation example of a digital tachograph for realizing a driving support function. 3 (a), 3 (b), and 3 (c) are front views showing specific examples of the relationship between each image frame obtained in different vehicle states and each detection frame assigned therein. Is. FIG. 4 is a flowchart showing an operation example of the digital tachograph for automatically determining the detection frame to be used according to the state of the vehicle. FIG. 5 is a schematic view showing a configuration example of the vehicle state table T1 referred to by the digital tachograph. FIG. 6 is a schematic diagram showing a configuration example of the detection frame table T2 referred to by the digital tachograph.

Specific embodiments of the present invention will be described below with reference to the respective figures.

<Overview of system configuration and operation>
FIG. 1 shows a configuration example of the operation management system 5 according to the embodiment of the present invention.
The operation management system 5 shown in FIG. 1 is introduced as equipment of a business operator such as a trucking company or a bus company. This operation management system 5 manages the operation status of each vehicle such as a truck or a bus, and includes an operation recording device (hereinafter referred to as a digital tachograph) 10 mounted on each vehicle as an on-board unit and each operator. It is composed of an office PC 30 installed in an office or the like. The digital tachograph 10 and the office PC 30 are connected so as to be able to communicate with each other via the network 70.

The office PC 30 is composed of a general-purpose computer device installed in the office and manages the operation status of the vehicle. The network 70 is a packet communication network such as the Internet to which a radio base station 8 and an office PC 30 that perform wide area communication with the digital tachograph 10 are connected, and relays data communication performed between the digital tachograph 10 and the office PC 30. .. Communication between the digital tachograph 10 and the wireless base station 8 may be performed by a mobile communication network (mobile line network) such as LTE (Long Term Evolution) / 4G (4th Generation), or a wireless LAN (Local Area). Network) may be used.

The digital tachograph 10 is mounted on a vehicle and records operation data such as entry / exit time, mileage, traveling time, traveling speed, speed over, engine speed over, sudden start, sudden acceleration, and sudden deceleration. In addition, the digital tachograph 10 of the present embodiment is equipped with a driving support function described later.

The digital tachograph 10 shown in FIG. 1 has a CPU (microcomputer) 11, a speed I / F (interface) 12A, an engine rotation I / F12B, an external input I / F13, a sensor input I / F14, and GPS reception as hardware. Unit 15, camera I / F16, non-volatile memory 26A, volatile memory 26B, recording unit 17, card I / F18, voice I / F19, RTC (clock IC) 21, SW input unit 22, communication unit 24, display unit 27, It also has a built-in analog input I / F29.

The CPU 11 comprehensively controls each part of the digital tachograph 10 according to a program incorporated in advance. The non-volatile memory 26A holds in advance an operation program executed by the CPU 11, constant data and tables referred to by the CPU 11. The non-volatile memory 26A is a memory in which data can be rewritten, and the retained data can be updated as needed.

The recording unit 17 records data such as operation data and video. A memory card 65 owned by the crew is freely inserted and removed from the card I / F18. The CPU 11 writes data such as operation data and video to the memory card 65 connected to the card I / F18. A built-in speaker 20 is connected to the voice I / F19. The speaker 20 emits a sound such as an alarm.

The RTC21 (timekeeping unit) measures the current time. ON / OFF signals of various buttons such as a warehousing button and a warehousing button are input to the SW input unit 22. The display unit 27 is composed of an LCD (liquid crystal display) and displays not only communication and operation status but also alarms and the like.

A vehicle speed sensor 51 that detects the speed of the vehicle is connected to the speed I / F 12A, and a speed pulse from the vehicle speed sensor 51 is input. The vehicle speed sensor 51 may be provided as an option in the digital tachograph 10, or may be provided as a device separate from the digital tachograph 10. A rotation pulse from an engine speed sensor (not shown) is input to the engine speed I / F12B.

External input I / F13 inputs include a brake signal indicating the on / off of the vehicle brake and a shift signal indicating the shift state (including forward / reverse distinction) of the automatic transmission from an external device (not shown). It is applied.

An acceleration sensor (G sensor) 28 that detects acceleration (G value) (sensing an impact) is connected to the sensor input I / F 14, and a signal from the G sensor 28 is input. Examples of the G sensor include those having a method of reading mechanical displacement due to acceleration as vibration and a method of reading optically, but the G sensor is not particularly limited. Further, the G sensor may detect an impact from the front of the vehicle (detecting deceleration G), may also detect an impact from the left-right direction (detect a lateral G), or may detect an impact from the rear of the vehicle. May be detected (acceleration G may be detected). The G sensor is composed of one or a plurality of sensors so as to be able to detect these accelerations.

Signals such as a temperature sensor (not shown) for detecting the engine temperature (cooling water temperature) and a fuel amount sensor (not shown) for detecting the amount of fuel are input to the analog input I / F29. The CPU 11 detects various operating states based on the information input via these I / Fs.

The GPS receiving unit 15 is connected to the GPS antenna 15a, receives radio waves of signals transmitted from GPS (Global Positioning System) satellites, and calculates and acquires information on the current position (GPS position information).

A plurality of in-vehicle cameras 23 and 23B are connected to the input of the camera I / F16. In the present embodiment, one of the in-vehicle cameras 23 is installed in the vehicle interior in a state of being fixed in a direction capable of photographing a scene such as a road ahead in the traveling direction of the own vehicle. Therefore, in the image captured by the vehicle-mounted camera 23, a preceding vehicle existing in front of the own vehicle, a white line indicating the boundary of the traveling lane during traveling, and a traffic regulation sign (speed limit, etc.) on the road surface appear. The other in-vehicle camera 23 is installed in the vehicle interior in a state of being fixed so as to be able to photograph a scene such as a road behind the own vehicle.

The in-vehicle cameras 23 and 23B have, for example, an image sensor in which 300,000 pixels, 1 million pixels, and 2 million pixels are arranged on an imaging surface imaged through a fisheye lens. The image sensor is composed of known sensors such as a CMOS (complementary metal oxide semiconductor) sensor and a CCD (charge-coupled device) sensor.

The video signals output by the in-vehicle cameras 23 and 23B are converted into digital signals representing the gradation and color of each pixel by the internal circuit of the camera I / F16, and output from the camera I / F16 as image data for each frame. NS.

The video (image data) captured by the in-vehicle cameras 23 and 23B is recorded as time-series data by the operation of the recording unit 17, but is repeatedly overwritten so as to be recorded for a predetermined time. This predetermined time is, for example, a time corresponding to several seconds (for example, 2 seconds, 4 seconds, 10 seconds, etc.) before and after the accident so that the situation of the accident can be understood at the time of the accident. The image captured by the camera 23 may be a still image or a moving image. The images before and after the accident are displayed on the display unit 33 of the office PC30.

Further, the digital tachograph 10 of the present embodiment is equipped with the following driving support functions (1) to (4), for example.
(1) A function that outputs an alarm when the distance between the own vehicle and the preceding vehicle is too close.
(2) A function that outputs an alarm when the own vehicle deviates from the range of the traveling lane in which the vehicle is traveling.
(3) A function that outputs an overspeed warning when the traveling speed of the own vehicle exceeds the speed limit indicated on the road surface.
(4) A function that notifies the driver of the existence of surrounding obstacles in situations such as when the own vehicle is reversing.

In order to realize each of the above functions (1) to (4), it is necessary to process the image data of the images taken by the in-vehicle cameras 23 and 23B to perform predetermined image recognition. That is, the position and distance of the preceding vehicle can be specified by image recognition, the relative position between the white line at the boundary of the traveling lane and the own vehicle can be detected, the speed limit of the road marking can be detected, and various obstacles can be detected. Is needed.

The above image recognition can be realized by executing a predetermined recognition algorithm according to a program in which the CPU 11 is incorporated. However, when the amount of data of the image to be processed is large, the load on the CPU 11 required for image recognition becomes very large, which makes real-time processing difficult and may cause a delay in detection. In particular, when the images of the plurality of in-vehicle cameras 23 and 23B are processed at the same time or when a plurality of recognition targets are detected at the same time, there is a concern that a delay may occur. Therefore, in the present embodiment, when executing image recognition, a detection frame is provided as described later to limit the data range to be processed, and special processing is performed according to the state of the vehicle.

When the communication unit 24 performs wide area communication and is connected to the radio base station 8 via the mobile line network (mobile communication network), the communication unit 24 and the office PC 30 are connected to the office PC 30 via a network 70 such as the Internet connected to the radio base station 8. Communicate. The power supply unit 25 supplies electric power to each unit of the digital tachograph 10 by turning on the ignition switch or the like.

On the other hand, the office PC 30 is composed of a PC (personal computer) that operates on a general-purpose operating system. The office PC 30 functions as an operation management device and has a CPU 31, a communication unit 32, a display unit 33, a storage unit 34, a card I / F35, an operation unit 36, an output unit 37, a voice I / F38, and an external I / F48. ..

The CPU 31 comprehensively controls each part of the office PC 30. The communication unit 32 can communicate with the digital tachograph 10 via the network 70. Further, the communication unit 32 can also connect to various databases (not shown) connected to the network 70, and can acquire necessary data.

The display unit 33 displays an accident image, a hazard map, and the like in addition to the operation management screen. The storage unit 34 holds various programs such as system analysis software for displaying the image received from the digital tachograph 10 and displaying the position information of the vehicle on the map.

A memory card 65 is freely inserted and removed from the card I / F35. The card I / F35 inputs the operation data measured by the digital tachograph 10 and stored in the memory card 65. The operation unit 36 has a keyboard, a mouse, and the like, and accepts operations by an office manager. The output unit 37 outputs various data. A microphone 41 and a speaker 42 are connected to the voice I / F 38. The office manager can also make a voice call using the microphone 41 and the speaker 42, and when a vehicle accident occurs, he / she contacts the emergency department or the police.

An external storage device (storage memory) 54 is connected to the external I / F 48. The external storage device 54 holds the accident point database (DB) 55, the operation data DB 56, and the hazard map DB 57. The GPS position information (latitude, longitude) of the vehicle at the time of the accident, which is transmitted from the digital tachograph 10, is registered in the accident point database (DB) 55. In the operation data DB 56, in addition to the entry / exit time, speed, mileage, etc., sudden acceleration / deceleration, sudden steering, speed over, engine speed over, etc. are recorded as operation data. In the hazard map DB 57, map data in which a mark indicating a point (accident point) where an accident occurred in the past is superimposed on the map is registered. In this hazard map, areas where disasters such as natural disasters are expected, evacuation sites, etc. may be described.

When the CPU 31 reads out the hazard map of the area designated from the hazard map DB 57 (for example, the area including the accident point) and displays it on the display unit 33, the CPU 31 acquires the data of the accident point registered in the accident point DB 55 and causes the hazard. A new hazard map is generated by superimposing marks representing these accident points on the map. Office managers can instantly see the latest accident points on a map (hazard map).

<Details of driving support function>
FIG. 2 shows an operation example of the digital tachograph 10 for realizing the driving support function. The operation shown in FIG. 2 is repeatedly executed by the CPU 11 in the digital tachograph 10 in a short time cycle.

In step S21, the CPU 11 executes a predetermined image recognition process on the image data of each frame corresponding to the images captured by the in-vehicle cameras 23 and 23B. However, the data to be processed is limited to the range of each detection frame predetermined in each image frame. The range of each detection frame can be specified by referring to, for example, the detection frame table T2A. The detection frame table T2A will be described later.

In step S22, the CPU 11 uses the recognition result of S21 to execute the inter-vehicle distance detection process. That is, the position of the preceding vehicle detected in the image frame and the positional relationship with the own vehicle are grasped, and the inter-vehicle distance is calculated based on the distance on the image and the shooting conditions of each camera. Further, the calculated inter-vehicle distance is compared with a predetermined threshold value, and when the inter-vehicle distance is too close, an inter-vehicle distance warning is output.

In step S23, the CPU 11 executes the lane deviation detection process by using the recognition result of S21. That is, by calculating the positional relationship and distance in the left-right direction between the position of the white line on the boundary of the traveling lane detected in the image frame and the position of the own vehicle, and comparing the result with a predetermined judgment condition, the lane is reached. Identify the presence or absence of deviation. Then, if there is a lane deviation, a lane deviation warning is output.

In step S24, the CPU 11 uses the recognition result of S21 to execute the overspeed detection process. That is, the presence or absence of overspeed is identified by comparing the speed limit recognized based on the speed limit marking on the road surface with the current running speed of the own vehicle. Then, if there is an overspeed, an overspeed warning is output.

In step S25, the CPU 11 uses the recognition result of S21 to execute a detection process other than the above. For example, the presence / absence of various obstacles, the presence / absence of moving objects, various boundary positions on the road, and the like are detected. Then, an alarm is output when an approach to an obstacle or a moving object is detected, or when the own vehicle approaches the boundary position.

<Relationship between image frame and detection frame>
Specific examples of the relationship between the image frames 100A, 100B, 100C obtained in different vehicle states and the detection frames assigned therein are shown in FIGS. 3 (a), 3 (b), and 3 (c). Each is shown in.

When the CPU 11 recognizes the image data obtained by shooting the in-vehicle cameras 23 and 23B, if the amount of image data is large, the processing load of the CPU 11 becomes large, the processing in real time becomes difficult, and a delay occurs. .. Therefore, in order to reduce the processing load of the CPU 11, the amount of data to be processed is reduced. Specifically, a detection frame that defines the range of data to be processed is provided.

Further, particularly when processing the image of the in-vehicle camera 23B that captures the rear view, the detection frame is optimized so as to be optimized according to whether the vehicle state is "backward", "stopped", or "forwarded". Change the total number of, the position of each detection frame, the size of each detection frame, etc. That is, the important points to be noted in the image frame differ depending on whether the vehicle state is "backward", "stopped", or "forwarded", so change it according to the vehicle state. Therefore, each detection frame can be minimized, and the amount of data to be processed can be effectively reduced.

3 (a), 3 (b), and 3 (c) are assigned to and within the respective image frames 100A, 100B, 100C in the "backward", "stopped", and "forwarded" states, respectively. A specific example of the relationship with each detection frame is shown.

In the image frame 100A shown in FIG. 3A, seven independent rectangular detection frames F11, F12, F13, F14, F15, F16, and F17 are assigned to different positions in the frame. Further, in the image frame 100B shown in FIG. 3B, five independent rectangular detection frames F21, F22, F23, F24, and F25 are assigned to different positions in the frame. Further, in the image frame 100C shown in FIG. 3C, two mutually independent rectangular detection frames F31 and F32 are assigned to different positions in the frame.

That is, when the own vehicle moves backward, attention is paid to various parts in the rear image, that is, the periphery behind the own vehicle and the destination in the traveling direction, as shown in the detection frames F11 to F17 shown in FIG. As a result, sufficient safety can be ensured when reversing. Further, when the own vehicle is stopped, the own vehicle is stopped by paying attention to the vicinity of the own vehicle at a short distance in the rear image as shown in the detection frames F21 to F25 shown in FIG. 3 (b). Sufficient safety can be ensured when starting to move from the state. Further, when the own vehicle is moving forward, as shown in the detection frames F31 and F32 shown in FIG. 3C, it is sufficient to pay attention only to the left and right sides at a short distance in the rear image to ensure sufficient safety on the rear side. Can be secured.

On the other hand, when the own vehicle is moving forward, it is indispensable to recognize the front image captured by the vehicle-mounted camera 23 at the same time as the rear image captured by the vehicle-mounted camera 23B, which increases the processing load of the CPU 11. Here, if the front image and the rear image are processed at the same time, the load on the CPU 11 further increases. However, by limiting the target range of image processing to only the detection frames F31 and F32 shown in FIG. 3C in the rear image, the amount of data to be processed can be reduced and an increase in load can be suppressed.

<Automatic switching of detection frame according to vehicle condition>
FIG. 4 shows an operation example of the digital tachograph 10 for automatically determining the detection frame to be used according to the state of the vehicle. That is, when the CPU 11 of the digital tachograph 10 executes the operation shown in FIG. 4, for example, the detection frame is automatically switched as shown in FIGS. 3 (a), 3 (b), and 3 (c). Realize. The operation of FIG. 4 will be described below.

In step S11, the CPU 11 identifies the forward / backward movement of the own vehicle. For example, by referring to the state of the shift signal obtained from the automatic transmission of the own vehicle, it is possible to distinguish whether the own vehicle is in the forward or backward state.

In step S12, the CPU 11 identifies whether or not the own vehicle is stopped. For example, it is possible to distinguish whether or not the vehicle is stopped based on the information on the current traveling speed of the own vehicle and the state of the brake signal.

In step S13, the CPU 11 distinguishes whether the own vehicle is in the "backward", "stopped", or "forward" state based on the results of S11 and S12. Then, in the case of "backward", the vehicle proceeds from S13 to S14, in the case of "stop", the vehicle proceeds from S13 to S15, and in the case of "forward", the vehicle proceeds from S13 to S16.

In step S14, the CPU 11 acquires constant data representing the detection frame combination at the time of reverse from the vehicle state table T1 and the detection frame table T2. The vehicle state table T1 and the detection frame table T2 will be described later.

In step S15, the CPU 11 acquires constant data representing the combination of detection frames when the vehicle is stopped from the vehicle state table T1 and the detection frame table T2. Further, in step S16, the CPU 11 acquires constant data representing the detection frame combination at the time of forward movement from the vehicle state table T1 and the detection frame table T2.

In step S17, the CPU 11 writes the constant data of the detection frame combination acquired in any of S14, S15, and S16 to the detection frame table T2A. The contents of the detection frame table T2A are reflected in the detection frame used in the process of step S21 shown in FIG. The detection frame table T2A may be omitted, and a part of the detection frame table T2 may be changed so as to be selectively used in the processing of S21.

<Configuration example of tables T1 and T2>
FIG. 5 shows a configuration example of the vehicle state table T1 referred to by the digital tachograph. Further, FIG. 6 shows a configuration example of the detection frame table T2 referred to by the digital tachograph.

The vehicle state table T1 shown in FIG. 5 holds constant data indicating the relationship between each state of “backward”, “stopped”, and “forward”, the number of detection frames N1, and the number N2 at the beginning of the detection frame. ing. In the vehicle state table T1 of FIG. 5, the number of detection frames N1 at the time of reverse is “7” as in the example shown in FIG. 3 (a). Further, as in the example shown in FIG. 3B, the number of detection frames N1 when the vehicle is stopped is “5”. Further, as in the example shown in FIG. 3C, the number of detection frames N1 at the time of advancing is “2”.

The detection frame table T2 shown in FIG. 6 holds constant data representing the relationship between the number N3, the reference position P, and the detection frame size S for each of the large number of detection frames. In this detection frame table T2, for example, the detection frame having the number N3 of "1" has a reference position P of P1, a constant indicating that the size in the X-axis direction is Sx1 and the size in the Y-axis direction is Sy1. Data is assigned.

For example, when the number N21 at the head of the detection frame in the vehicle state table T1 shown in FIG. 5 is "1", the constant data in the range of "1" to "7" for the number N3 in the detection frame table T2 is It is selected in S14 of FIG. 4 as a combination of detection frames when reversing. Therefore, the positions and the vertical / horizontal sizes of the seven detection frames F11 to F17 shown in FIG. 3A in each frame can be specified.

Further, when the number N22 at the head of the detection frame in the vehicle state table T1 shown in FIG. 5 is “8”, the constant data in the range of the numbers N3 in the detection frame table T2 from “8” to “12” is generated. It is selected in S15 of FIG. 4 as a combination of detection frames when the vehicle is stopped. Therefore, the position and the vertical / horizontal size of each of the five detection frames F21 to F25 shown in FIG. 3B can be specified.

Further, when the number N23 at the head of the detection frame in the vehicle state table T1 shown in FIG. 5 is “13”, the constant data in the range of the numbers N3 in the detection frame table T2 from “13” to “14” is generated. It is selected in S16 of FIG. 4 as a combination of detection frames when moving forward. Therefore, the positions and the vertical / horizontal sizes of the two detection frames F31 to F32 shown in FIG. 3C in each frame can be specified.

A part of the data extracted from the detection frame table T2 in any of S14, S15, and S16 is written to the detection frame table T2A, and the contents of the detection frame table T2A are reflected in the process of step S21 of FIG. .. Therefore, as shown in FIGS. 3 (a), 3 (b), and 3 (c), the actual state of the own vehicle is actually "backward", "stopped", or "forward". The number, position, size, etc. of the detection frame used for can be automatically switched.

The vehicle state table T1 and the detection frame table T2 are arranged in a storage area on the non-volatile memory 26A, and each constant data held by them is changed as necessary. For example, when the in-vehicle camera 23B is newly installed in the own vehicle or the position is changed, the administrator can execute the special software for adjusting each parameter of the digital tachograph 10 on the CPU 11 so that the administrator can set the vehicle status table. T1 and the detection frame table T2 can be updated.

<Possibility of deformation>
In the examples shown in FIGS. 3 (a), 3 (b), and 3 (c), only the detection frame for processing the image of the in-vehicle camera 23B that captures the rear is assumed, but the front is captured. It is expected that the same detection frame will be applied to reduce the amount of data to be processed when processing the image of the in-vehicle camera 23 or another in-vehicle camera that captures the side of the vehicle or the interior of the vehicle. .. Then, for example, when the own vehicle moves backward, the load on the CPU 11 is reduced by reducing the number and size of the detection frames used in the process of recognizing the image in front, and the delay in the process of recognizing the image in the rear is reduced. Can be suppressed.

<Advantages of Digital Tachograph 10>
In the digital tachograph 10 shown in FIG. 1, in order to realize the driving support function, when the operation shown in FIG. 2 is executed, for example, when the own vehicle is moving forward, the detection frame is used in step S21. As a result, the load on the CPU 11 for processing the rear image can be significantly reduced. As a result, even when trying to realize multiple types of driving support functions (inter-vehicle distance warning, lane departure warning, overspeed warning, etc.) at the same time based on the image taken in front, a high-performance CPU Real-time processing without delay becomes possible without using. Further, for example, when the own vehicle moves backward, the number of detection frames used when processing the rear image can be increased in S14 as shown in FIG. 3A, so that the safety of the rear can be sufficiently ensured. ..

Here, the features of the on-board unit and the driving support device according to the above-described embodiment of the present invention are briefly summarized and listed below in [1] to [5], respectively.
[1] An image processing unit (CPU11, S21) that inputs and processes a video signal output by one or more in-vehicle cameras (23, 23B) mounted on the vehicle, and an image processing unit (CPU11, S21).
A vehicle state detection unit (CPU11, S11, S12) that detects at least one state of the vehicle running or not and a traveling direction, and
An image area determination unit (CPU11, S13 to S16) that dynamically determines an area in the video signal processed by the image processing unit, and
Have,
The image area determination unit automatically changes the area (S17, S21), reflecting the detection state of the vehicle state detection unit.
An in-vehicle device characterized by that.

[2] The image area determination unit is
A constant holding unit (detection frame table) that holds constant data representing the positions and sizes of a plurality of two-dimensional regions (detection frames F11 to F17, F21 to F25, F31, and F32) allocated in advance in the video signal. Has T2)
One or more two-dimensional regions selected according to the detection state of the vehicle state detection unit from the plurality of two-dimensional regions are assigned as regions in the video signal processed by the image processing unit (S17). ,
The on-board unit according to the above [1].

[3] The image area determination unit automatically determines the number of two-dimensional areas to be selected from the plurality of two-dimensional areas and a combination thereof according to the detection state of the vehicle state detection unit (S13 to S13). S16),
The in-vehicle device according to the above [2].

[4] The image area determination unit recognizes one of the forward, backward, and stopped states of the vehicle based on the detection state of the vehicle state detection unit, and the above-mentioned according to the recognized state of the vehicle. The area is automatically changed (S13 to S16),
The vehicle-mounted device according to any one of the above [1] to [3].

[5] The on-board unit according to any one of the above [1] to [4] and the in-vehicle device.
An alarm generation unit (S22 to S25) that generates an alarm that supports safe driving of the vehicle based on the result recognized by the image processing unit from the video signal and a predetermined determination criterion.
A driving support device characterized by being equipped with.

5 Operation management system 8 Wireless base station 10 Digital tachograph 11, 31 CPU
12A Speed I / F
12B engine rotation I / F
13 External input I / F
14 Sensor input I / F
15 GPS receiver 15a GPS antenna 16 Camera I / F
17 Recording unit 18 Card I / F
19 Voice I / F
20, 42 speakers 21 RTC
22 SW input unit 23 In-vehicle camera 24, 32 Communication unit 25 Power supply unit 26A Non-volatile memory 26B Volatile memory 27 Display unit 28 G sensor 29 Analog input I / F
30 office PC
33 Display unit 34 Storage unit 35 Card I / F
36 Operation unit 37 Output unit 38 Voice I / F
41 Microphone 48 External I / F
51 Vehicle speed sensor 54 External storage device 55 Accident point DB
56 Operation data DB
57 Hazard map DB
65 Memory card 70 Network 100A, 100B, 100C Image frame F11, F12, F13, F14, F15, F16, F17 Detection frame F21, F22, F23, F24, F25, F31, F32 Detection frame T1 Vehicle status table T2, T2A detection Frame table

Claims (5)

An image processing unit that inputs and processes video signals output by an in-vehicle camera that can shoot the rear of the vehicle,
A vehicle condition detection unit that detects at least one of the presence / absence of traveling and the traveling direction of the vehicle, and
An image area determination unit that dynamically determines an area in the video signal processed by the image processing unit, and an image area determination unit.
Have,
The image area determination unit, reflecting the detection state of the vehicle state detection unit, automatically changing the area,
The image area determination unit recognizes one of the forward, backward, and stopped states of the vehicle based on the detection state of the vehicle state detection unit.
The image processing unit processes the number or size of the regions processed by the image processing unit when the forward movement of the vehicle is recognized, when the backward movement of the vehicle is recognized and when the stop of the vehicle is recognized. Less than the number or size of the regions,
An in-vehicle device characterized by that. The image area determination unit
It has a constant holding unit that holds constant data representing the position and size of each of a plurality of two-dimensional regions allocated in advance in the video signal.
One or more two-dimensional regions selected according to the detection state of the vehicle state detection unit from the plurality of two-dimensional regions are allocated as regions in the video signal processed by the image processing unit.
The vehicle-mounted device according to claim 1. The image area determination unit automatically determines the number of two-dimensional areas to be selected from the plurality of two-dimensional areas and a combination thereof according to the detection state of the vehicle state detection unit.
The on-board unit according to claim 2. The number or size of the regions processed by the image processing unit when recognizing the stop of the vehicle is smaller than the number or size of the regions processed by the image processing unit when recognizing the retreat of the vehicle.
The vehicle-mounted device according to any one of claims 1 to 3, wherein the vehicle-mounted device is characterized by the above. The on-board unit according to any one of claims 1 to 4.
An alarm generation unit that generates an alarm that supports safe driving of the vehicle based on the result recognized by the image processing unit from the video signal and a predetermined determination criterion.
A driving support device characterized by being equipped with.

Images